Dr. Yuncheng Jiang, Professor

School of Computer Science and School of Artificial Intelligence, South China Normal University, Guangzhou, China

Biography

Dr. Yuncheng Jiang is a Professor at the School of Computer Science and the School of Artificial Intelligence, South China Normal University, Guangdong, China, and named among the World’s Top 2% Scientists (Stanford University list, 2024 and 2025). He received his Ph.D. from the Institute of Computing Technology, Chinese Academy of Sciences in 2004. His research has been published in journals and conferences including TOIS, TKDE, TNNLS, TEC, IPM, TLT, TCSS, TBD, TCE, AAAI, IJCAI, ACM MM, CIKM, ECML PKDD, DASFAA, and AIED. He was a recipient of the Best Paper Awards at KSEM 2022 and CSIS-IAC 2024, and the Special Session Best Paper Awards at ADMA 2024 and 2025. He is a member of the KSEM (International Conference on Knowledge Science, Engineering and Management) steering committee, and the chair of IEEE Task Force on Educational Data Mining, the vice chairs of IEEE Guangzhou Section Computer Society Chapter, ACM Guangzhou Chapter and CCF Guangzhou Chapter, a distinguished membership of China Computer Federation (CCF), and a council member of the Chinese Association for Artificial Intelligence (CAAI). He also is the General Co-Chair of NCTCS 2023 and AIEC 2026, the PC Co-Chairs of PRICAI 2026, KSEM 2023, and CAAI DMAI 2023, 2024 and 2025, the Workshop chair of PRICAI 2024, the chairs of IWEAI 2024, 2025 and 2026, and the Track chairs of Special Track on Data Intelligence & Knowledge Mining at ADMA 2024 and 2025. His current research interests include graph computing, multimodal learning, multimodal knowledge graphs, educational artificial intelligence and data science.

Topic

Knowledge Tracing Models Based on Deep Learning and MLLMs

Abstract

Knowledge Tracing is one of the key technologies enabling intelligent education. Based on multimodal interactive data and process data such as students’ historical problem-solving sequences, it dynamically infers learners’ mastery level of each knowledge concept and predicts their future performance on exercises. It serves as the core underlying algorithm for adaptive learning and personalized learning, as well as the infrastructure for various downstream tasks in intelligent education, including exercise recommendation, learning assessment, and learning situation analysis. This talk mainly analyzes the current research progress of Knowledge Tracing, and particularly presents the latest work completed by my research team in recent years, with a focus on diverse Knowledge Tracing methods based on deep learning and multimodal large language models.